ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning

TL;DR

ConfigX introduces a universal, modular configuration framework for evolutionary algorithms using multitask reinforcement learning, enabling robust zero-shot generalization and efficient lifelong adaptation across diverse optimization tasks.

Contribution

It presents a novel modular system and Transformer-based meta-learning approach to create a universal configuration agent for various EAs, improving adaptability and performance.

Findings

Achieves robust zero-shot generalization to unseen tasks.

Outperforms state-of-the-art baselines in experiments.

Demonstrates strong lifelong learning and adaptation capabilities.

Abstract

Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enhancing their performance and adaptability across various BBO instances. However, they are often tailored to a specific EA, which limits their generalizability and necessitates retraining or redesigns for different EAs and optimization problems. To address this limitation, we introduce ConfigX, a new paradigm of the MetaBBO framework that is capable of learning a universal configuration agent (model) for boosting diverse EAs. To achieve so, our ConfigX first leverages a novel modularization system that enables the flexible combination of various optimization sub-modules to generate diverse EAs during training. Additionally, we propose a Transformer-based neural network to meta-learn a universal configuration policy through multitask reinforcement learning across a designed joint optimization task space. Extensive experiments verify that, our ConfigX, after large-scale pre-training, achieves robust zero-shot generalization to unseen tasks and outperforms state-of-the-art baselines. Moreover, ConfigX exhibits strong lifelong learning capabilities, allowing efficient adaptation to new tasks through fine-tuning. Our proposed ConfigX represents a significant step toward an automatic, all-purpose configuration agent for EAs.